Video: https://vimeo.com/190728913 Many types of multi-dimensional data have a natural division into two “views”, such as audio and video or images and text. Multi-view learning refers to techniques that use multiple views of data to learn improved models for each of the views. Theoretical and empirical results indicate that multi-view …
Video: https://vimeo.com/189163584 Mixed-integer convex optimization problems are convex problems with the additional (non-convex) constraints that some variables may take only integer values. Despite the past decades’ advances in algorithms and technology for both mixed-integer *linear* and *continuous, convex* optimization, mixed-integer convex optimization problems have remained relatively more challenging and less …
Video: https://vimeo.com/189185951 Fluorescence light-sheet microscopy such as Selective Plane Illumination Microscopy (SPIM) [1] is a powerful tool to image developmental processes in vivo with high-resolution over large tissue volumes [2]. The main advantages of the technology are the minimal phototoxicity due to the confined fluorescence excitation and the fast full-frame …
Video: https://vimeo.com/185807382 Stochastic processes with dynamics at multiple time scales are pervasive in science and engineering. In neuroscience experiments, the spiking dynamics of neurons can exhibit variability both within a given trial (fast time scale) and across trials (fast time scale). The behavior of users on social media often exhibits …
Video: https://vimeo.com/185052120 I will talk about three simple combinatorial ideas to speed up parallel and distributed learning algorithms. We will start off with serial equivalence in asynchronous parallel ML, its significance, and how we can guarantee it using a recent phase transition result on graphs. We continue on the issue …
Video: https://vimeo.com/184352560 Concepts in geometry often have parallels in information theory; for example, volume and entropy, surface area and Fisher information, sphere-packing and channel coding, and Euclidean balls and Gaussian distributions, to name a few. These similarities provide a simple way to posit theorems in one area by translating the …
Video: https://vimeo.com/183315365 Projected gradient descent (PGD), and its close variants, are often considered the method of choice for solving a very large variety of machine learning optimization problems, including sparse recovery problems, empirical risk minimization, stochastic optimization, and online convex optimization. This is not surprising, since PGD is often optimal …
Video: https://vimeo.com/154897631 We use CVaR to create a general framework for computing compromise solutions in a multi-objective, multi-stakeholder setting. In this setting, we sample the preferences of a population of stakeholders and we observe that the stakeholder dissatisfactions (distance to their utopia points) can be interpreted as random variables. Consequently, …
Video Recording: https://vimeo.com/153826086 Our quest is to derive convex relaxations for the pooling problem, a nonconvex production planning problem in which products are mixed in intermediate pools in order to meet quality targets at their destinations. The story begins with a description of the problem and discussion of state-of-the-art solution …
Video Recording: https://vimeo.com/154227289 We are in the midst of a 3D revolution. Robots enabled by 3D cameras are beginning to autonomously drive cars, perform surgeries, and manage factories. However, when deployed in the real-world, these cameras face several challenges that prevent them from measuring 3D shape reliably. These challenges include …